Are you sure you want to delete this task? Once this task is deleted, it cannot be recovered.
Miao Zheng 104429be00 | 1 year ago | |
---|---|---|
.. | ||
README.md | 1 year ago | |
fastfcn.yml | 1 year ago | |
fastfcn_r50-d32_jpu_aspp_4x4_512x1024_80k_cityscapes.py | 2 years ago | |
fastfcn_r50-d32_jpu_aspp_512x512_80k_ade20k.py | 2 years ago | |
fastfcn_r50-d32_jpu_aspp_512x512_160k_ade20k.py | 2 years ago | |
fastfcn_r50-d32_jpu_aspp_512x1024_80k_cityscapes.py | 2 years ago | |
fastfcn_r50-d32_jpu_enc_4x4_512x1024_80k_cityscapes.py | 2 years ago | |
fastfcn_r50-d32_jpu_enc_512x512_80k_ade20k.py | 2 years ago | |
fastfcn_r50-d32_jpu_enc_512x512_160k_ade20k.py | 2 years ago | |
fastfcn_r50-d32_jpu_enc_512x1024_80k_cityscapes.py | 2 years ago | |
fastfcn_r50-d32_jpu_psp_4x4_512x1024_80k_cityscapes.py | 2 years ago | |
fastfcn_r50-d32_jpu_psp_512x512_80k_ade20k.py | 2 years ago | |
fastfcn_r50-d32_jpu_psp_512x512_160k_ade20k.py | 2 years ago | |
fastfcn_r50-d32_jpu_psp_512x1024_80k_cityscapes.py | 2 years ago |
FastFCN: Rethinking Dilated Convolution in the Backbone for Semantic Segmentation
Modern approaches for semantic segmentation usually employ dilated convolutions in the backbone to extract high-resolution feature maps, which brings heavy computation complexity and memory footprint. To replace the time and memory consuming dilated convolutions, we propose a novel joint upsampling module named Joint Pyramid Upsampling (JPU) by formulating the task of extracting high-resolution feature maps into a joint upsampling problem. With the proposed JPU, our method reduces the computation complexity by more than three times without performance loss. Experiments show that JPU is superior to other upsampling modules, which can be plugged into many existing approaches to reduce computation complexity and improve performance. By replacing dilated convolutions with the proposed JPU module, our method achieves the state-of-the-art performance in Pascal Context dataset (mIoU of 53.13%) and ADE20K dataset (final score of 0.5584) while running 3 times faster.
@article{wu2019fastfcn,
title={Fastfcn: Rethinking dilated convolution in the backbone for semantic segmentation},
author={Wu, Huikai and Zhang, Junge and Huang, Kaiqi and Liang, Kongming and Yu, Yizhou},
journal={arXiv preprint arXiv:1903.11816},
year={2019}
}
Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU | mIoU(ms+flip) | config | download |
---|---|---|---|---|---|---|---|---|---|
FastFCN + DeepLabV3 | R-50-D32 | 512x1024 | 80000 | 5.67 | 2.64 | 79.12 | 80.58 | config | model | log |
FastFCN + DeepLabV3 (4x4) | R-50-D32 | 512x1024 | 80000 | 9.79 | - | 79.52 | 80.91 | config | model | log |
FastFCN + PSPNet | R-50-D32 | 512x1024 | 80000 | 5.67 | 4.40 | 79.26 | 80.86 | config | model | log |
FastFCN + PSPNet (4x4) | R-50-D32 | 512x1024 | 80000 | 9.94 | - | 78.76 | 80.03 | config | model | log |
FastFCN + EncNet | R-50-D32 | 512x1024 | 80000 | 8.15 | 4.77 | 77.97 | 79.92 | config | model | log |
FastFCN + EncNet (4x4) | R-50-D32 | 512x1024 | 80000 | 15.45 | - | 78.6 | 80.25 | config | model | log |
Method | Backbone | Crop Size | Lr schd | Mem (GB) | Inf time (fps) | mIoU | mIoU(ms+flip) | config | download |
---|---|---|---|---|---|---|---|---|---|
FastFCN + DeepLabV3 | R-50-D32 | 512x512 | 80000 | 8.46 | 12.06 | 41.88 | 42.91 | config | model | log |
FastFCN + DeepLabV3 | R-50-D32 | 512x512 | 160000 | - | - | 43.58 | 44.92 | config | model | log |
FastFCN + PSPNet | R-50-D32 | 512x512 | 80000 | 8.02 | 19.21 | 41.40 | 42.12 | config | model | log |
FastFCN + PSPNet | R-50-D32 | 512x512 | 160000 | - | - | 42.63 | 43.71 | config | model | log |
FastFCN + EncNet | R-50-D32 | 512x512 | 80000 | 9.67 | 17.23 | 40.88 | 42.36 | config | model | log |
FastFCN + EncNet | R-50-D32 | 512x512 | 160000 | - | - | 42.50 | 44.21 | config | model | log |
Note:
4x4
means 4 GPUs with 4 samples per GPU in training, default setting is 4 GPUs with 2 samples per GPU in training.No Description
Python Markdown Shell Dockerfile other
Dear OpenI User
Thank you for your continuous support to the Openl Qizhi Community AI Collaboration Platform. In order to protect your usage rights and ensure network security, we updated the Openl Qizhi Community AI Collaboration Platform Usage Agreement in January 2024. The updated agreement specifies that users are prohibited from using intranet penetration tools. After you click "Agree and continue", you can continue to use our services. Thank you for your cooperation and understanding.
For more agreement content, please refer to the《Openl Qizhi Community AI Collaboration Platform Usage Agreement》